© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164119
    Prev
    Next
    INDEX
    Explanations

    strengthening transparency or understanding

    np_acts-logits-general · gemini-2.5-flash-lite

    efficiency and consistency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كله
    0.52
    👭
    0.50
    hesus
    0.50
    <unused553>
    0.49
     பார்த்த
    0.49
     ઘર
    0.46
    <unused2109>
    0.46
     Allí
    0.46
    <unused539>
    0.46
    ProductsStore
    0.45
    POSITIVE LOGITS
     qualific
    0.50
     epidemi
    0.48
     mon
    0.46
     scre
    0.46
     capitalism
    0.45
     virulence
    0.45
     rational
    0.45
     ser
    0.45
     opl
    0.45
     assertion
    0.44
    Activations Density 0.001%

    No Known Activations